pip install transformers datasets evaluate

>>> from huggingface_hub import notebook_login

>>> notebook_login()

>>> from datasets import load_dataset

>>> swag = load_dataset("allenai/swag", "regular")

>>> swag["train"][0]
{'ending0': 'passes by walking down the street playing their instruments.',
 'ending1': 'has heard approaching them.',
 'ending2': "arrives and they're outside dancing and asleep.",
 'ending3': 'turns the lead singer watches the performance.',
 'fold-ind': '3416',
 'gold-source': 'gold',
 'label': 0,
 'sent1': 'Members of the procession walk down the street holding small horn brass instruments.',
 'sent2': 'A drum line',
 'startphrase': 'Members of the procession walk down the street holding small horn brass instruments. A drum line',
 'video-id': 'anetv_jkn6uvmqwh4'}

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")

>>> ending_names = ["ending0", "ending1", "ending2", "ending3"]


>>> def preprocess_function(examples):
...     first_sentences = [[context] * 4 for context in examples["sent1"]]
...     question_headers = examples["sent2"]
...     second_sentences = [
...         [f"{header} {examples[end][i]}" for end in ending_names] for i, header in enumerate(question_headers)
...     ]

...     first_sentences = sum(first_sentences, [])
...     second_sentences = sum(second_sentences, [])

...     tokenized_examples = tokenizer(first_sentences, second_sentences, truncation=True)
...     return {k: [v[i : i + 4] for i in range(0, len(v), 4)] for k, v in tokenized_examples.items()}

>>> tokenized_swag = swag.map(preprocess_function, batched=True)

>>> from transformers import DataCollatorForMultipleChoice
>>> collator = DataCollatorForMultipleChoice(tokenizer=tokenizer)

>>> import evaluate

>>> accuracy = evaluate.load("accuracy")

>>> import numpy as np


>>> def compute_metrics(eval_pred):
...     predictions, labels = eval_pred
...     predictions = np.argmax(predictions, axis=1)
...     return accuracy.compute(predictions=predictions, references=labels)

>>> from transformers import AutoModelForMultipleChoice, TrainingArguments, Trainer

>>> model = AutoModelForMultipleChoice.from_pretrained("google-bert/bert-base-uncased")

>>> training_args = TrainingArguments(
...     output_dir="my_awesome_swag_model",
...     eval_strategy="epoch",
...     save_strategy="epoch",
...     load_best_model_at_end=True,
...     learning_rate=5e-5,
...     per_device_train_batch_size=16,
...     per_device_eval_batch_size=16,
...     num_train_epochs=3,
...     weight_decay=0.01,
...     push_to_hub=True,
... )

>>> trainer = Trainer(
...     model=model,
...     args=training_args,
...     train_dataset=tokenized_swag["train"],
...     eval_dataset=tokenized_swag["validation"],
...     processing_class=tokenizer,
...     data_collator=collator,
...     compute_metrics=compute_metrics,
... )

>>> trainer.train()

>>> trainer.push_to_hub()

>>> prompt = "France has a bread law, Le Décret Pain, with strict rules on what is allowed in a traditional baguette."
>>> candidate1 = "The law does not apply to croissants and brioche."
>>> candidate2 = "The law applies to baguettes."

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("username/my_awesome_swag_model")
>>> inputs = tokenizer([[prompt, candidate1], [prompt, candidate2]], return_tensors="pt", padding=True)
>>> labels = torch.tensor(0).unsqueeze(0)

>>> from transformers import AutoModelForMultipleChoice

>>> model = AutoModelForMultipleChoice.from_pretrained("username/my_awesome_swag_model")
>>> outputs = model(**{k: v.unsqueeze(0) for k, v in inputs.items()}, labels=labels)
>>> logits = outputs.logits

>>> predicted_class = logits.argmax().item()
>>> predicted_class
0